该楼层疑似违规已被系统折叠 隐藏此楼查看此楼

import requests

from multiprocessing import Pool

import re

import json

from requests.exceptions import ConnectionError

def get_to_html(url):

try:

headers = {"User-Agent": "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0;"}

response = requests.get(url,headers=headers)

# print(response)

if response.status_code ==200:

return response.content.decode("utf-8")

return None

except ConnectionError:

return None

def parse_index(html):

pattern = re.compile('

.*?board-index.*?>#(\d+).*?.*?data-src="(.*?)".*?name">(.*?)'

+'.*?start">(.*?)

releasetime">(.*?).*?integer">(.*?).*?fracion">(.*?).*?',re.S)

items=re.findall(pattern,html)

for item in items:

yield {

"index":item[0],

"image":item[1],

"name":item[2],

"actor":item[3].strip()[3:],

"releasetime":item[4].strip()[5:],

"count":item[5]+item[6]

}

def write_to_file(content):

with open("maoyan.txt","a") as f:

content = json.dumps(content,ensure_ascii=False)+'\n'

f.write(content,encoding ="utf-8")

def main():

url="https://maoyan.com/board/4"

html=get_to_html(url)

items=parse_index(html)

for item in items:

write_to_file(item)

if __name__ =="__main__":

# pool=Pool()

# pool.map(main)

main()